Merge tag 'zonefs-5.10-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/dlemoal/zonefs

Pull zonefs updates from Damien Le Moal:
 "Add an 'explicit-open' mount option to automatically issue a
  REQ_OP_ZONE_OPEN command to the device whenever a sequential zone file
  is open for writing for the first time.

  This avoids 'insufficient zone resources' errors for write operations
  on some drives with limited zone resources or on ZNS drives with a
  limited number of active zones. From Johannes"

* tag 'zonefs-5.10-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/dlemoal/zonefs:
  zonefs: document the explicit-open mount option
  zonefs: open/close zone on file open/close
  zonefs: provide no-lock zonefs_io_error variant
  zonefs: introduce helper for zone management

Author: torvalds

Documentation/filesystems/zonefs.rst

@@ -326,6 +326,21 @@ discover the amount of data that has been written to the zone. In the case of a
 read-only zone discovered at run-time, as indicated in the previous section.
 The size of the zone file is left unchanged from its last updated value.
 
+A zoned block device (e.g. an NVMe Zoned Namespace device) may have limits on
+the number of zones that can be active, that is, zones that are in the
+implicit open, explicit open or closed conditions.  This potential limitation
+translates into a risk for applications to see write IO errors due to this
+limit being exceeded if the zone of a file is not already active when a write
+request is issued by the user.
+
+To avoid these potential errors, the "explicit-open" mount option forces zones
+to be made active using an open zone command when a file is opened for writing
+for the first time. If the zone open command succeeds, the application is then
+guaranteed that write requests can be processed. Conversely, the
+"explicit-open" mount option will result in a zone close command being issued
+to the device on the last close() of a zone file if the zone is not full nor
+empty.
+
 Zonefs User Space Tools
 =======================
 

fs/zonefs/super.c

@@ -24,6 +24,39 @@
 
 #include "zonefs.h"
 
+static inline int zonefs_zone_mgmt(struct inode *inode,
+				   enum req_opf op)
+{
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	int ret;
+
+	lockdep_assert_held(&zi->i_truncate_mutex);
+
+	ret = blkdev_zone_mgmt(inode->i_sb->s_bdev, op, zi->i_zsector,
+			       zi->i_zone_size >> SECTOR_SHIFT, GFP_NOFS);
+	if (ret) {
+		zonefs_err(inode->i_sb,
+			   "Zone management operation %s at %llu failed %d\n",
+			   blk_op_str(op), zi->i_zsector, ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static inline void zonefs_i_size_write(struct inode *inode, loff_t isize)
+{
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+
+	i_size_write(inode, isize);
+	/*
+	 * A full zone is no longer open/active and does not need
+	 * explicit closing.
+	 */
+	if (isize >= zi->i_max_size)
+		zi->i_flags &= ~ZONEFS_ZONE_OPEN;
+}
+
 static int zonefs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 			      unsigned int flags, struct iomap *iomap,
 			      struct iomap *srcmap)
@@ -301,6 +334,17 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
 		}
 	}
 
+	/*
+	 * If the filesystem is mounted with the explicit-open mount option, we
+	 * need to clear the ZONEFS_ZONE_OPEN flag if the zone transitioned to
+	 * the read-only or offline condition, to avoid attempting an explicit
+	 * close of the zone when the inode file is closed.
+	 */
+	if ((sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN) &&
+	    (zone->cond == BLK_ZONE_COND_OFFLINE ||
+	     zone->cond == BLK_ZONE_COND_READONLY))
+		zi->i_flags &= ~ZONEFS_ZONE_OPEN;
+
 	/*
 	 * If error=remount-ro was specified, any error result in remounting
 	 * the volume as read-only.
@@ -315,7 +359,7 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
 	 * invalid data.
 	 */
 	zonefs_update_stats(inode, data_size);
-	i_size_write(inode, data_size);
+	zonefs_i_size_write(inode, data_size);
 	zi->i_wpoffset = data_size;
 
 	return 0;
@@ -328,7 +372,7 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
  * eventually correct the file size and zonefs inode write pointer offset
  * (which can be out of sync with the drive due to partial write failures).
  */
-static void zonefs_io_error(struct inode *inode, bool write)
+static void __zonefs_io_error(struct inode *inode, bool write)
 {
 	struct zonefs_inode_info *zi = ZONEFS_I(inode);
 	struct super_block *sb = inode->i_sb;
@@ -342,8 +386,6 @@ static void zonefs_io_error(struct inode *inode, bool write)
 	};
 	int ret;
 
-	mutex_lock(&zi->i_truncate_mutex);
-
 	/*
 	 * Memory allocations in blkdev_report_zones() can trigger a memory
 	 * reclaim which may in turn cause a recursion into zonefs as well as
@@ -359,7 +401,14 @@ static void zonefs_io_error(struct inode *inode, bool write)
 		zonefs_err(sb, "Get inode %lu zone information failed %d\n",
 			   inode->i_ino, ret);
 	memalloc_noio_restore(noio_flag);
+}
 
+static void zonefs_io_error(struct inode *inode, bool write)
+{
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+
+	mutex_lock(&zi->i_truncate_mutex);
+	__zonefs_io_error(inode, write);
 	mutex_unlock(&zi->i_truncate_mutex);
 }
 
@@ -397,13 +446,27 @@ static int zonefs_file_truncate(struct inode *inode, loff_t isize)
 	if (isize == old_isize)
 		goto unlock;
 
-	ret = blkdev_zone_mgmt(inode->i_sb->s_bdev, op, zi->i_zsector,
-			       zi->i_zone_size >> SECTOR_SHIFT, GFP_NOFS);
-	if (ret) {
-		zonefs_err(inode->i_sb,
-			   "Zone management operation at %llu failed %d",
-			   zi->i_zsector, ret);
+	ret = zonefs_zone_mgmt(inode, op);
+	if (ret)
 		goto unlock;
+
+	/*
+	 * If the mount option ZONEFS_MNTOPT_EXPLICIT_OPEN is set,
+	 * take care of open zones.
+	 */
+	if (zi->i_flags & ZONEFS_ZONE_OPEN) {
+		/*
+		 * Truncating a zone to EMPTY or FULL is the equivalent of
+		 * closing the zone. For a truncation to 0, we need to
+		 * re-open the zone to ensure new writes can be processed.
+		 * For a truncation to the maximum file size, the zone is
+		 * closed and writes cannot be accepted anymore, so clear
+		 * the open flag.
+		 */
+		if (!isize)
+			ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_OPEN);
+		else
+			zi->i_flags &= ~ZONEFS_ZONE_OPEN;
 	}
 
 	zonefs_update_stats(inode, isize);
@@ -584,7 +647,7 @@ static int zonefs_file_write_dio_end_io(struct kiocb *iocb, ssize_t size,
 		mutex_lock(&zi->i_truncate_mutex);
 		if (i_size_read(inode) < iocb->ki_pos + size) {
 			zonefs_update_stats(inode, iocb->ki_pos + size);
-			i_size_write(inode, iocb->ki_pos + size);
+			zonefs_i_size_write(inode, iocb->ki_pos + size);
 		}
 		mutex_unlock(&zi->i_truncate_mutex);
 	}
@@ -865,8 +928,128 @@ static ssize_t zonefs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	return ret;
 }
 
+static inline bool zonefs_file_use_exp_open(struct inode *inode, struct file *file)
+{
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb);
+
+	if (!(sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN))
+		return false;
+
+	if (zi->i_ztype != ZONEFS_ZTYPE_SEQ)
+		return false;
+
+	if (!(file->f_mode & FMODE_WRITE))
+		return false;
+
+	return true;
+}
+
+static int zonefs_open_zone(struct inode *inode)
+{
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb);
+	int ret = 0;
+
+	mutex_lock(&zi->i_truncate_mutex);
+
+	zi->i_wr_refcnt++;
+	if (zi->i_wr_refcnt == 1) {
+
+		if (atomic_inc_return(&sbi->s_open_zones) > sbi->s_max_open_zones) {
+			atomic_dec(&sbi->s_open_zones);
+			ret = -EBUSY;
+			goto unlock;
+		}
+
+		if (i_size_read(inode) < zi->i_max_size) {
+			ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_OPEN);
+			if (ret) {
+				zi->i_wr_refcnt--;
+				atomic_dec(&sbi->s_open_zones);
+				goto unlock;
+			}
+			zi->i_flags |= ZONEFS_ZONE_OPEN;
+		}
+	}
+
+unlock:
+	mutex_unlock(&zi->i_truncate_mutex);
+
+	return ret;
+}
+
+static int zonefs_file_open(struct inode *inode, struct file *file)
+{
+	int ret;
+
+	ret = generic_file_open(inode, file);
+	if (ret)
+		return ret;
+
+	if (zonefs_file_use_exp_open(inode, file))
+		return zonefs_open_zone(inode);
+
+	return 0;
+}
+
+static void zonefs_close_zone(struct inode *inode)
+{
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	int ret = 0;
+
+	mutex_lock(&zi->i_truncate_mutex);
+	zi->i_wr_refcnt--;
+	if (!zi->i_wr_refcnt) {
+		struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb);
+		struct super_block *sb = inode->i_sb;
+
+		/*
+		 * If the file zone is full, it is not open anymore and we only
+		 * need to decrement the open count.
+		 */
+		if (!(zi->i_flags & ZONEFS_ZONE_OPEN))
+			goto dec;
+
+		ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_CLOSE);
+		if (ret) {
+			__zonefs_io_error(inode, false);
+			/*
+			 * Leaving zones explicitly open may lead to a state
+			 * where most zones cannot be written (zone resources
+			 * exhausted). So take preventive action by remounting
+			 * read-only.
+			 */
+			if (zi->i_flags & ZONEFS_ZONE_OPEN &&
+			    !(sb->s_flags & SB_RDONLY)) {
+				zonefs_warn(sb, "closing zone failed, remounting filesystem read-only\n");
+				sb->s_flags |= SB_RDONLY;
+			}
+		}
+		zi->i_flags &= ~ZONEFS_ZONE_OPEN;
+dec:
+		atomic_dec(&sbi->s_open_zones);
+	}
+	mutex_unlock(&zi->i_truncate_mutex);
+}
+
+static int zonefs_file_release(struct inode *inode, struct file *file)
+{
+	/*
+	 * If we explicitly open a zone we must close it again as well, but the
+	 * zone management operation can fail (either due to an IO error or as
+	 * the zone has gone offline or read-only). Make sure we don't fail the
+	 * close(2) for user-space.
+	 */
+	if (zonefs_file_use_exp_open(inode, file))
+		zonefs_close_zone(inode);
+
+	return 0;
+}
+
 static const struct file_operations zonefs_file_operations = {
-	.open		= generic_file_open,
+	.open		= zonefs_file_open,
+	.release	= zonefs_file_release,
 	.fsync		= zonefs_file_fsync,
 	.mmap		= zonefs_file_mmap,
 	.llseek		= zonefs_file_llseek,
@@ -890,6 +1073,7 @@ static struct inode *zonefs_alloc_inode(struct super_block *sb)
 	inode_init_once(&zi->i_vnode);
 	mutex_init(&zi->i_truncate_mutex);
 	init_rwsem(&zi->i_mmap_sem);
+	zi->i_wr_refcnt = 0;
 
 	return &zi->i_vnode;
 }
@@ -940,14 +1124,15 @@ static int zonefs_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 enum {
 	Opt_errors_ro, Opt_errors_zro, Opt_errors_zol, Opt_errors_repair,
-	Opt_err,
+	Opt_explicit_open, Opt_err,
 };
 
 static const match_table_t tokens = {
 	{ Opt_errors_ro,	"errors=remount-ro"},
 	{ Opt_errors_zro,	"errors=zone-ro"},
 	{ Opt_errors_zol,	"errors=zone-offline"},
 	{ Opt_errors_repair,	"errors=repair"},
+	{ Opt_explicit_open,	"explicit-open" },
 	{ Opt_err,		NULL}
 };
 
@@ -984,6 +1169,9 @@ static int zonefs_parse_options(struct super_block *sb, char *options)
 			sbi->s_mount_opts &= ~ZONEFS_MNTOPT_ERRORS_MASK;
 			sbi->s_mount_opts |= ZONEFS_MNTOPT_ERRORS_REPAIR;
 			break;
+		case Opt_explicit_open:
+			sbi->s_mount_opts |= ZONEFS_MNTOPT_EXPLICIT_OPEN;
+			break;
 		default:
 			return -EINVAL;
 		}
@@ -1403,6 +1591,13 @@ static int zonefs_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_gid = GLOBAL_ROOT_GID;
 	sbi->s_perm = 0640;
 	sbi->s_mount_opts = ZONEFS_MNTOPT_ERRORS_RO;
+	sbi->s_max_open_zones = bdev_max_open_zones(sb->s_bdev);
+	atomic_set(&sbi->s_open_zones, 0);
+	if (!sbi->s_max_open_zones &&
+	    sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN) {
+		zonefs_info(sb, "No open zones limit. Ignoring explicit_open mount option\n");
+		sbi->s_mount_opts &= ~ZONEFS_MNTOPT_EXPLICIT_OPEN;
+	}
 
 	ret = zonefs_read_super(sb);
 	if (ret)

fs/zonefs/zonefs.h

@@ -38,6 +38,8 @@ static inline enum zonefs_ztype zonefs_zone_type(struct blk_zone *zone)
 	return ZONEFS_ZTYPE_SEQ;
 }
 
+#define ZONEFS_ZONE_OPEN	(1 << 0)
+
 /*
  * In-memory inode data.
  */
@@ -74,6 +76,10 @@ struct zonefs_inode_info {
 	 */
 	struct mutex		i_truncate_mutex;
 	struct rw_semaphore	i_mmap_sem;
+
+	/* guarded by i_truncate_mutex */
+	unsigned int		i_wr_refcnt;
+	unsigned int		i_flags;
 };
 
 static inline struct zonefs_inode_info *ZONEFS_I(struct inode *inode)
@@ -154,6 +160,7 @@ enum zonefs_features {
 #define ZONEFS_MNTOPT_ERRORS_MASK	\
 	(ZONEFS_MNTOPT_ERRORS_RO | ZONEFS_MNTOPT_ERRORS_ZRO | \
 	 ZONEFS_MNTOPT_ERRORS_ZOL | ZONEFS_MNTOPT_ERRORS_REPAIR)
+#define ZONEFS_MNTOPT_EXPLICIT_OPEN	(1 << 4) /* Explicit open/close of zones on open/close */
 
 /*
  * In-memory Super block information.
@@ -175,6 +182,9 @@ struct zonefs_sb_info {
 
 	loff_t			s_blocks;
 	loff_t			s_used_blocks;
+
+	unsigned int		s_max_open_zones;
+	atomic_t		s_open_zones;
 };
 
 static inline struct zonefs_sb_info *ZONEFS_SB(struct super_block *sb)